© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4072
    Prev
    Next
    INDEX
    Explanations

    api id assignment

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires strongly on rare or salient content words (i.e. meaningful nouns, verbs, or adjectives) rather than on common function words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rotl
    0.83
     DFT
    0.79
     отсутствие
    0.79
    硌
    0.77
     inextricably
    0.77
    âns
    0.76
    僮
    0.76
     NTFS
    0.76
     Painlev
    0.75
     घूम
    0.75
    POSITIVE LOGITS
     化学
    0.73
    ווה
    0.70
    OVE
    0.67
    ly
    0.66
     云
    0.64
     fetch
    0.63
     条
    0.63
    ंध्र
    0.61
    ઠી
    0.61
    庆
    0.61
    Activations Density 0.000%

    No Known Activations